Skip to content
ModelListedExternal
Download

RALL NoCrop Ori16F 8B16F GACWDlr

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5065 Accuracy: 0.7952

Sourcehuggingface.co/TanAlexanderlz/RALL_NoCrop_ori16F-8B16F-GACWDlr/tree/13bcce6be6b485763adad3de2739a8bdcbf8939d
KindOtherBase modelMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 13bcce6

Model source

Kind
Other
File size
329 MB
Base model
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 13bcce6
Updated
Sep 17, 2026
Downloads
5
Source
Hugging Face

Source description

RALL_NoCrop_ori16F-8B16F-GACWDlr

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5065
  • Accuracy: 0.7952

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 768

Training results

Training LossEpochStepValidation LossAccuracy
0.65770.0625480.65990.5828
0.58041.0625960.59640.6687
0.46642.06251440.54300.7362
0.32423.06251920.50260.7607
0.31444.06252400.51470.7791
0.26195.06252880.54420.7730
0.18786.06253360.53960.7791
0.15827.06253840.54960.7791
0.17048.06254320.58340.7730
0.14749.06254800.60930.7914
0.141710.06255280.60540.7914
0.129911.06255760.67550.7791
0.092312.06256240.68020.7791
0.114813.06256720.66290.7914
0.131214.06257200.68190.7914

Framework versions

  • Transformers 4.52.2
  • Pytorch 2.6.0+cu124
  • Datasets 2.14.4
  • Tokenizers 0.21.1

Sources

1 source
Hugging FacePrimaryVersion 13bcce6be6b485763adad3de2739a8bdcbf8939d
huggingface.co/TanAlexanderlz/RALL_NoCrop_ori16F-8B16F-GACWDlr/tree/13bcce6be6b485763adad3de2739a8bdcbf8939d

Verified Sep 5

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 44bae3eff55c…2110 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 5huggingface.co/TanAlexanderlz/RALL_NoCrop_ori16F-8B16F-GACWDlr

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy model-index: - name: RALL_NoCrop_ori16F-8B16F-GACWDlr results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # RALL_NoCrop_ori16F-8B16F-GACWDlr This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5065 - Accuracy: 0.7952 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 768 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 0.6577 | 0.0625 | 48 | 0.6599 | 0.5828 | | 0.5804 | 1.0625 | 96 | 0.5964 | 0.6687 | | 0.4664 | 2.0625 | 144 | 0.5430 | 0.7362 | | 0.3242 | 3.0625 | 192 | 0.5026 | 0.7607 | | 0.3144 | 4.0625 | 240 | 0.5147 | 0.7791 | | 0.2619 | 5.0625 | 288 | 0.5442 | 0.7730 | | 0.1878 | 6.0625 | 336 | 0.5396 | 0.7791 | | 0.1582 | 7.0625 | 384 | 0.5496 | 0.7791 | | 0.1704 | 8.0625 | 432 | 0.5834 | 0.7730 | | 0.1474 | 9.0625 | 480 | 0.6093 | 0.7914 | | 0.1417 | 10.0625 | 528 | 0.6054 | 0.7914 | | 0.1299 | 11.0625 | 576 | 0.6755 | 0.7791 | | 0.0923 | 12.0625 | 624 | 0.6802 | 0.7791 | | 0.1148 | 13.0625 | 672 | 0.6629 | 0.7914 | | 0.1312 | 14.0625 | 720 | 0.6819 | 0.7914 | ### Framework versions - Transformers 4.52.2 - Pytorch 2.6.0+cu124 - Datasets 2.14.4 - Tokenizers 0.21.1

NoteSep 5huggingface.co/TanAlexanderlz/RALL_NoCrop_ori16F-8B16F-GACWDlr

Source context: 5 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo TanAlexanderlz/RALL_NoCrop_ori16F-8B16F-GACWDlr